7 ファイル変更+16-11
この更新の概要
Vertex AIにおけるMCPツール検索機能が、Claude Sonnet 4.5およびOpus 4.5以降のモデルでサポートされるようになりました。/feedbackコマンドの仕様が変更され、送信する会話履歴の期間（セッションのみ、24時間、7日間）を選択できる機能が追加されています。BedrockやVertex AIなどのサードパーティプロバイダー利用時には、フィードバック内容がローカルの専用ディレクトリに保存される仕組みが導入されました。各環境におけるツール検索の有効化条件や、エラー発生時の報告手順に関する記述が最新の仕様に合わせて整理されています。
Vertex AI環境においてSonnet 4.5およびOpus 4.5以降でツール検索がサポートされたことと、環境変数による上書き時の挙動が追記されました。
@@ -28,12 +28,12 @@ Tool search requires Claude Sonnet 4 or later, or Claude Opus 4 or later. Haiku
## Configure tool search
Tool search is on by default. It is disabled by default on Vertex AI, which does not accept the tool search beta header, and when `ANTHROPIC_BASE_URL` points to a non-first-party host, since most proxies do not forward `tool_reference` blocks. You can override this with the `ENABLE_TOOL_SEARCH` environment variable:
Tool search is on by default. It is disabled by default on Vertex AI, where it is supported for Claude Sonnet 4.5 and later and Claude Opus 4.5 and later. It is also disabled when `ANTHROPIC_BASE_URL` points to a non-first-party host, since most proxies do not forward `tool_reference` blocks. You can override either default with the `ENABLE_TOOL_SEARCH` environment variable:
| Value | Behavior |
| :- | :- |
| (unset) | Tool search is on. Tool definitions are deferred and discovered on demand. Falls back to loading upfront on Vertex AI or a non-first-party `ANTHROPIC_BASE_URL`. |
| `true` | Tool search is always on. The SDK sends the beta header even on Vertex AI and through proxies. Requests fail if the backend or proxy does not support `tool_reference` blocks. |
| `true` | Tool search is always on. The SDK sends the beta header even on Vertex AI and through proxies. Requests fail on Vertex AI models earlier than Sonnet 4.5 or Opus 4.5, or on proxies that do not support `tool_reference` blocks. |
| `auto` | Checks the combined token count of all tool definitions against the model's context window. If they exceed 10%, tool search activates. If they're under 10%, all tools are loaded into context normally. |
| `auto:N` | Same as `auto` with a custom percentage. `auto:5` activates when tool definitions exceed 5% of the context window. Lower values activate sooner. |
| `false` | Tool search is off. All tool definitions are loaded into context on every turn. |
@@ -102,6 +102,7 @@ Files in the paths below are deleted on startup once they're older than [`cleanu
| `tasks/` | Per-session task lists written by the task tools |
| `shell-snapshots/` | Captured shell environment used by the Bash tool. Removed on clean exit. The sweep clears any left after a crash. |
| `backups/` | Timestamped copies of `~/.claude.json` taken before config migrations |
| `feedback-bundles/` | Redacted transcript archives written by `/feedback` on third-party providers, for sending to your Anthropic account team |
### Kept until you delete them
@@ -98,7 +98,9 @@ Claude Code connects from users' machines to Anthropic to log operational metric
Claude Code connects from users' machines to Sentry for operational error logging. The data is encrypted in transit using TLS and at rest using 256-bit AES encryption. Read more in the [Sentry security documentation](https://sentry.io/security/). To opt out of error logging, set the `DISABLE_ERROR_REPORTING` environment variable.
When users run the `/feedback` command, a copy of their full conversation history including code is sent to Anthropic. The data is encrypted in transit via TLS. Optionally, a GitHub issue is created in the public repository. To opt out, set the `DISABLE_FEEDBACK_COMMAND` environment variable to `1`.
When you run the `/feedback` command, a copy of your conversation history including code is sent to Anthropic. Before submitting, you choose how much history to include: the current session only, which is the default, or also other sessions from the same project over the last 24 hours or 7 days. The data is encrypted in transit via TLS. Optionally, a GitHub issue is created in the public repository. To opt out, set the `DISABLE_FEEDBACK_COMMAND` environment variable to `1`.
When you use a third-party provider such as Bedrock or Vertex, or have no Anthropic credentials configured, `/feedback` writes the report to a local archive under `~/.claude/feedback-bundles/` instead of sending it to Anthropic. Known API key and token patterns are redacted before the archive is written. Nothing leaves your machine until you send that file to your Anthropic account representative or attach it to a support request.
## Default behaviors by API provider
@@ -211,7 +211,7 @@ Claude Code supports the following environment variables to control its behavior
| `ENABLE_CLAUDEAI_MCP_SERVERS` | Set to `false` to disable [claude.ai MCP servers](/en/mcp#use-mcp-servers-from-claude-ai) in Claude Code. Enabled by default for logged-in users |
| `ENABLE_PROMPT_CACHING_1H` | Set to `1` to request a 1-hour prompt cache TTL instead of the default 5 minutes. Intended for API key, [Bedrock](/en/amazon-bedrock), [Vertex](/en/google-vertex-ai), [Foundry](/en/microsoft-foundry), and [Claude Platform on AWS](/en/claude-platform-on-aws) users. Subscription users receive 1-hour TTL automatically. 1-hour cache writes are billed at a higher rate |
| `ENABLE_PROMPT_CACHING_1H_BEDROCK` | Deprecated. Use `ENABLE_PROMPT_CACHING_1H` instead |
| `ENABLE_TOOL_SEARCH` | Controls [MCP tool search](/en/mcp#scale-with-mcp-tool-search). Unset: all MCP tools deferred by default, but loaded upfront on Vertex AI or when `ANTHROPIC_BASE_URL` points to a non-first-party host. Values: `true` (always defer and send the beta header, requests fail on Vertex AI or proxies that do not support `tool_reference`), `auto` (threshold mode: load upfront if tools fit within 10% of context), `auto:N` (custom threshold, e.g., `auto:5` for 5%), `false` (load all upfront) |
| `ENABLE_TOOL_SEARCH` | Controls [MCP tool search](/en/mcp#scale-with-mcp-tool-search). Unset: all MCP tools deferred by default, but loaded upfront on Vertex AI or when `ANTHROPIC_BASE_URL` points to a non-first-party host. Values: `true` (always defer and send the beta header; supported on Vertex AI with Sonnet 4.5 and later or Opus 4.5 and later; requests fail on earlier Vertex AI models or on proxies that do not support `tool_reference`), `auto` (threshold mode: load upfront if tools fit within 10% of context), `auto:N` (custom threshold, e.g., `auto:5` for 5%), `false` (load all upfront) |
| `FALLBACK_FOR_ALL_PRIMARY_MODELS` | Set to any non-empty value to trigger fallback to [`--fallback-model`](/en/cli-reference#cli-flags) after repeated overload errors on any primary model. By default, only Opus models trigger the fallback |
| `FORCE_AUTOUPDATE_PLUGINS` | Set to `1` to force plugin auto-updates even when the main auto-updater is disabled via `DISABLE_AUTOUPDATER` |
| `FORCE_PROMPT_CACHING_5M` | Set to `1` to force the 5-minute prompt cache TTL even when 1-hour TTL would otherwise apply. Overrides `ENABLE_PROMPT_CACHING_1H` |
@@ -80,7 +80,7 @@ This indicates an unexpected failure inside the API. It is not caused by your pr
- Check [status.claude.com](https://status.claude.com) for active incidents
- Wait a minute, then send your message again. Your original message is still in the conversation, so for a long prompt you can type `try again` instead of pasting the whole thing.
- If the error persists with no posted incident, run `/feedback` so Anthropic can investigate with your request details. See [Report an error](#report-an-error) if `/feedback` is unavailable on your provider.
- If the error persists with no posted incident, run `/feedback` so Anthropic can investigate with your request details. See [Report an error](#report-an-error) if `/feedback` is unavailable in your environment.
### API Error: Repeated 529 Overloaded errors
@@ -583,7 +583,7 @@ Check these first:
When a response goes wrong, rewinding usually works better than replying with corrections. Press Esc twice or run `/rewind` to step back to before the bad turn, then rephrase the prompt with more specifics. Correcting in-thread keeps the wrong attempt in context, which can anchor later answers to it. See [Checkpointing](/en/checkpointing).
If quality still seems off after checking the above, run `/feedback` and describe what you expected versus what you got. Feedback submitted this way includes the conversation transcript, which is the fastest way for Anthropic to diagnose a real regression. See [Report an error](#report-an-error) if `/feedback` is unavailable on your provider.
If quality still seems off after checking the above, run `/feedback` and describe what you expected versus what you got. Feedback submitted this way includes the conversation transcript, which is the fastest way for Anthropic to diagnose a real regression. See [Report an error](#report-an-error) if `/feedback` is unavailable in your environment.
## Report an error
@@ -595,7 +595,7 @@ This page covers errors from the Claude API. For errors from other Claude Code c
If an error is not listed here or the suggested fix does not help:
- Run `/feedback` inside Claude Code to send the transcript and a description to Anthropic. The command also offers to open a prefilled GitHub issue. Feedback is unavailable on Bedrock, Vertex AI, and Foundry deployments.
- Run `/feedback` inside Claude Code to send the transcript and a description to Anthropic. The command also offers to open a prefilled GitHub issue. On Bedrock, Vertex AI, Foundry, and other third-party providers, `/feedback` saves a local archive you can send to your Anthropic account representative instead.
- Run `/doctor` to check for local configuration problems
- Check [status.claude.com](https://status.claude.com) for active incidents
- Search [existing issues](https://github.com/anthropics/claude-code/issues) on GitHub
@@ -187,7 +187,7 @@ Most model versions have a corresponding `VERTEX_REGION_CLAUDE_*` variable. See
[Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) is enabled automatically. To disable it, set `DISABLE_PROMPT_CACHING=1`. To request a 1-hour cache TTL instead of the 5-minute default, set `ENABLE_PROMPT_CACHING_1H=1`; cache writes with a 1-hour TTL are billed at a higher rate. For heightened rate limits, contact Google Cloud support. When using Vertex AI, the `/login` and `/logout` commands are disabled since authentication is handled through Google Cloud credentials.
[MCP tool search](/en/mcp#scale-with-mcp-tool-search) is disabled by default on Vertex AI because the endpoint does not accept the required beta header. All MCP tool definitions load upfront instead. Setting `ENABLE_TOOL_SEARCH=true` forces Claude Code to send the header anyway, which causes Vertex AI to reject requests.
Claude Code disables [MCP tool search](/en/mcp#scale-with-mcp-tool-search) by default on Vertex AI, so MCP tool definitions load upfront. Vertex AI supports tool search for Claude Sonnet 4.5 and later and Claude Opus 4.5 and later. Set `ENABLE_TOOL_SEARCH=true` to enable it on those models. Earlier models on Vertex AI do not accept the required beta header, and requests fail if you enable tool search with them.
### 5. Pin model versions
@@ -848,16 +848,18 @@ Claude Code truncates tool descriptions and server instructions at 2KB each. Kee
### Configure tool search
Tool search is enabled by default: MCP tools are deferred and discovered on demand. It is disabled by default on Vertex AI, which does not accept the tool search beta header, and when `ANTHROPIC_BASE_URL` points to a non-first-party host, since most proxies do not forward `tool_reference` blocks. If your proxy forwards `tool_reference` blocks, set `ENABLE_TOOL_SEARCH` explicitly to override the fallback. This feature requires models that support `tool_reference` blocks: Sonnet 4 and later, or Opus 4 and later. Haiku models do not support tool search.
Tool search is enabled by default: MCP tools are deferred and discovered on demand. Claude Code disables it by default on Vertex AI. It is also disabled when `ANTHROPIC_BASE_URL` points to a non-first-party host, since most proxies do not forward `tool_reference` blocks. Set `ENABLE_TOOL_SEARCH` explicitly to override either fallback.
Tool search requires a model that supports `tool_reference` blocks: Sonnet 4 and later, or Opus 4 and later. Haiku models do not support it. On Vertex AI, tool search is supported for Claude Sonnet 4.5 and later and Claude Opus 4.5 and later.
Control tool search behavior with the `ENABLE_TOOL_SEARCH` environment variable:
| Value | Behavior |
| :- | :- |
| (unset) | All MCP tools deferred and loaded on demand. Falls back to loading upfront on Vertex AI or when `ANTHROPIC_BASE_URL` is a non-first-party host |
| `true` | All MCP tools deferred. Claude Code sends the beta header even on Vertex AI and through proxies. Requests fail if the backend does not support `tool_reference` blocks |
| `true` | All MCP tools deferred. Claude Code sends the beta header even on Vertex AI and through proxies. Requests fail on Vertex AI models earlier than Sonnet 4.5 or Opus 4.5, or on proxies that do not support `tool_reference` blocks |
| `auto` | Threshold mode: tools load upfront if they fit within 10% of the context window, deferred otherwise |
| `auto:<N>` | Threshold mode with a custom percentage, where `<N>` is 0-100 (e.g., `auto:5` for 5%) |
| `auto:N` | Threshold mode with a custom percentage, where `N` is 0-100. For example, `auto:5` for 5% |
| `false` | All MCP tools loaded upfront, no deferral |
```bash